Weather AI Research Engineer — Model Evaluation & Systems

Convectivecapital; Redwood City (CA); Hybrid; USD 140,000 - 240,000; Full time

Benefits offered by this job

401(k)

Dental, health, and vision insurance

Unlimited PTO

Stock Option Plan

Office food and beverages

Job summary

WindBorne Systems is developing AI weather models that run 24/7 and forecast globally every 20 minutes. We seek a Machine Learning Research Engineer to define robust evaluation strategies, build fast, reproducible analyses, and extend tooling for model comparison across regions and weather regimes.

You will present clear results with uncertainty caveats and collaborate with meteorology and research teams to shape the next generation of forecasts. Hybrid or in‑person work in Redwood City, CA.

Qualifications

• Excellent scientific judgment and healthy skepticism.
• Strong experimental taste and ability to identify evaluation that answers the question that matters.
• Systems thinking to build reusable infrastructure for future work.
• Experience evaluating ML systems using geospatial, time‑series, or multi‑dimensional datasets.
• Able to investigate ambiguous results, synthesize evidence, and communicate conclusions clearly.
• Experience with weather, climate, forecasting, or AI‑assisted research tools is helpful.

Responsibilities

• Evaluation strategy — Develop a rigorous, meteorologically valid strategy for comparing WeatherMesh with leading models. Select metrics, datasets, baselines, case studies.
• Fast feedback and durable systems — Build quick evaluations that provide useful signals and scale into reusable infrastructure.
• Agentic tooling for evals — Improve our evaluation infrastructure, including agentic AI tools for forecasts and results.
• Technical communication — Produce clear scorecards, visualizations, and explanations for researchers, leadership, customers, and partners.

Skills

Python

ML tools

Geospatial data

Time-series

Experimental design

Communication

Tools

PyTorch

NumPy

pandas

xarray

Job description

WindBorne Systems is developing AI weather models that run 24/7 and forecast globally every 20 minutes. We seek a Machine Learning Research Engineer to define robust evaluation strategies, build fast, reproducible analyses, and extend tooling for model comparison across regions and weather regimes.

You will present clear results with uncertainty caveats and collaborate with meteorology and research teams to shape the next generation of forecasts. Hybrid or in‑person work in Redwood City, CA.